Research map / Vision-language and multimodal / Multimodal LLMs
Towards Language-Guided Visual Recognition via Dynamic Convolutions
Gen Luo, Yiyi Zhou, Xiaoshuai Sun, Yongjian Wu, Yue Gao, Rongrong Ji
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| scale LaConvNet-S up to LaConvNet-B (10 to 19 blocks) (ablation) | LaConvNet · RefCOCO val (REC) | IoU@0.5 accuracy: 80.26 -> 82.46 | Improved |
| scale LaConvNet-S up to LaConvNet-B (ablation) | LaConvNet · RefCOCO+ val (REC) | IoU@0.5 accuracy: 69.82 -> 72.31 | Improved |
| scale LaConvNet-S up to LaConvNet-B (ablation) | LaConvNet · RefCOCO+ val (RES) | IoU: 57.16 -> 60.43 | Improved |
| scale LaConvNet-S up to LaConvNet-B (ablation) | LaConvNet · CLEVR-Ref+ | IoU: 79.8 -> 82.3 | Improved |
| scale LaConvNet-S up to LaConvNet-B (ablation) | LaConvNet · gRefCOCO val | N-acc: 59.16 -> 58.06 | Hurt |
| replace TransVG (168M params) with LaConvNet-B (35M params) | TransVG · RefCOCO+ val (REC) | IoU@0.5 accuracy: 64.82 -> 72.31 | Improved |
| replace TransVG with LaConvNet-B | TransVG · RefCOCO testB (REC) | IoU@0.5 accuracy: 78.35 -> 78.16 | No clear effect |
| replace pre-trained VILLA-L with LaConvNet-B | VILLA-L · RefCOCO+ val (REC) | IoU@0.5 accuracy: 76.17 -> 72.31 | Hurt |
| replace IEP-Ref (with ground-truth programs) with LaConvNet-B, no program labels | IEP-Ref · CLEVR-Ref+ | IoU: 81.6 -> 82.3 | Improved |
| replace LAVT (Swin-T) with LaConvNet-B | LAVT · RefCOCO+ val (RES) | IoU: 57.02 -> 60.43 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- TransVG — TransVG: End-to-End Visual Grounding With Transformers (ICCV 2021) · better on 6 of 7 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Analyzing and Boosting the Power of Fine-Grained Visual Recognition for Multi-modal Large Language Models (ICLR 2025 · similarity 0.88)
- Dynamic Multimodal Evaluation with Flexible Complexity by Vision-Language Bootstrapping (ICLR 2025 · similarity 0.88)
- Frozen Transformers in Language Models Are Effective Visual Encoder Layers (ICLR 2024 · similarity 0.87)
- MoDA: Modulation Adapter for Fine-Grained Visual Understanding in Instructional MLLMs (ICML 2026 · similarity 0.87)
- Image as a Language: Revisiting Scene Text Recognition via Balanced, Unified and Synchronized Vision-Language Reasoning Network (AAAI 2024 · similarity 0.87)
- Cross-modal Information Flow in Multimodal Large Language Models (CVPR 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
